Choose a focused solution or see All

Powerfully Simple Trade Promotion Forecasting

Promotions, advertising and other forms of “demand shaping” can be enormously expensive, costing more than 20% of gross revenues for some businesses. Yet determining their actual impact or “lift” remains a daunting supply chain problem. A large number of variables with complex interactions are buried in huge amounts of data with a high degree of noise. Even with substantial expertise and fairly consistent baseline demand, it’s usually not possible to understand the correlations among the variables.

To solve this problem, we turned to a powerful technology called machine learning (Rulex®). This technique makes it possible to recognize the shared characteristics of promotional events and identify their effect on normal sales. It extracts knowledge about which variables most impact demand and produces a set of simple intelligible rules, easily understood by the user. Fast multi-dimensional modelling identifies each rule’s relevance and importance, its range and its cut-offs. It handles both qualitative and quantitative variables.

This breakthrough technique creates a major improvement in demand visibility, forecast quality and level of forecast detail. It also improves customer service levels and reduces obsolescence costs.

Read Case Study Promotion and Media Forecasting
Read Case Study Supply Chain Planning with Heavy Promotional Influence
Watch Video Three Reasons Why Trade Promotion Forecasting is Difficult